Model comparison
Qwen3.6-35B-A3B vs Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
At Q4_K_M, Qwen3.6-35B-A3B is the smaller download — 21,166,757,728 bytes against 24,253,604,896. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 4.8× smaller, which usually matters more than the difference in weights.
From the file· summed bytes, KV per layer
Side by side
| Qwen3.6-35B-A3B | Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking | |
|---|---|---|
| Parameters | 36.0B | 39.5B |
| Architecture | qwen35moe | qwen35 |
| Layers | 40 | 96 |
| Native context | 262,144 | 262,144 |
| Mixture of experts | yes, 256 experts | no |
| Quantizations published | 61 | 30 |
| Smallest quantization | 8.77 GiB | 13.76 GiB |
| Q4_K_M | 19.71 GiB | 22.59 GiB |
| Licence | apache-2.0 | apache-2.0 |
KV cache by context
the term that decides long-context viability
| Context | Qwen3.6-35B-A3B | Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking | Ratio |
|---|---|---|---|
| 4,096 | 0.08 GiB | 0.38 GiB | 4.80× |
| 8,192 | 0.16 GiB | 0.75 GiB | 4.80× |
| 16,384 | 0.31 GiB | 1.50 GiB | 4.80× |
| 32,768 | 0.63 GiB | 3.00 GiB | 4.80× |
| 65,536 | 1.25 GiB | 6.00 GiB | 4.80× |
| 131,072 | 2.50 GiB | 12.00 GiB | 4.80× |